Update README.md
Browse files
README.md
CHANGED
@@ -12,16 +12,8 @@ Currently released models:
|
|
12 |
|
13 |
**ZeroDiffusion-Inpaint v0.9** (zd_inpaint_v0-9 and zd_inpaint_v0-9_ema) - an experimental finetune of the stable-diffusion-inpainting model, initialized from a merge of ZD 0.9
|
14 |
|
15 |
-
This is a work in progress model trained off of SD 1.5 with zero terminal SNR.
|
16 |
-
|
17 |
-
ZeroDiffusion v0.9 is intended as a final prototype made from a complete training run.
|
18 |
-
|
19 |
-
ZeroDiffusion v1.0 will most likely start training if/when SD 1.6 model weights are released.
|
20 |
-
|
21 |
The intention of this model is to provide a training base for other models, and to provide researchers with a clean model base to test zero terminal SNR with.
|
22 |
|
23 |
For this model to work well, you will probably need CFG rescale, which is implemented in this plugin: https://github.com/Seshelle/CFG_Rescale_webui
|
24 |
|
25 |
-
Dynamic Thresholding is another potential alternative to CFG rescale which on the right settings will stabilize images and also not cause the brownout often caused by CFG rescale, however it will require more tweaking to work. Get Dynamic Thresholding for A1111 here: https://github.com/mcmonkeyprojects/sd-dynamic-thresholding/
|
26 |
-
|
27 |
You must also download the corresponding YAML file and put it in the folder with the model (assuming you are using A1111's webui or similar). It won't work without it. It will tell webui to use the model in v-prediction mode.
|
|
|
12 |
|
13 |
**ZeroDiffusion-Inpaint v0.9** (zd_inpaint_v0-9 and zd_inpaint_v0-9_ema) - an experimental finetune of the stable-diffusion-inpainting model, initialized from a merge of ZD 0.9
|
14 |
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
The intention of this model is to provide a training base for other models, and to provide researchers with a clean model base to test zero terminal SNR with.
|
16 |
|
17 |
For this model to work well, you will probably need CFG rescale, which is implemented in this plugin: https://github.com/Seshelle/CFG_Rescale_webui
|
18 |
|
|
|
|
|
19 |
You must also download the corresponding YAML file and put it in the folder with the model (assuming you are using A1111's webui or similar). It won't work without it. It will tell webui to use the model in v-prediction mode.
|